From 925d1c401fa6cfd0df5d2e37da8981494ccdec07 Mon Sep 17 00:00:00 2001 From: Matt Helsley Date: Tue, 29 Apr 2008 01:01:36 -0700 Subject: procfs task exe symlink The kernel implements readlink of /proc/pid/exe by getting the file from the first executable VMA. Then the path to the file is reconstructed and reported as the result. Because of the VMA walk the code is slightly different on nommu systems. This patch avoids separate /proc/pid/exe code on nommu systems. Instead of walking the VMAs to find the first executable file-backed VMA we store a reference to the exec'd file in the mm_struct. That reference would prevent the filesystem holding the executable file from being unmounted even after unmapping the VMAs. So we track the number of VM_EXECUTABLE VMAs and drop the new reference when the last one is unmapped. This avoids pinning the mounted filesystem. [akpm@linux-foundation.org: improve comments] [yamamoto@valinux.co.jp: fix dup_mmap] Signed-off-by: Matt Helsley Cc: Oleg Nesterov Cc: David Howells Cc:"Eric W. Biederman" Cc: Christoph Hellwig Cc: Al Viro Cc: Hugh Dickins Signed-off-by: YAMAMOTO Takashi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) (limited to 'fs/proc/base.c') diff --git a/fs/proc/base.c b/fs/proc/base.c index c5e412a00b17..b48ddb119945 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1181,6 +1181,81 @@ static const struct file_operations proc_pid_sched_operations = { #endif +/* + * We added or removed a vma mapping the executable. The vmas are only mapped + * during exec and are not mapped with the mmap system call. + * Callers must hold down_write() on the mm's mmap_sem for these + */ +void added_exe_file_vma(struct mm_struct *mm) +{ + mm->num_exe_file_vmas++; +} + +void removed_exe_file_vma(struct mm_struct *mm) +{ + mm->num_exe_file_vmas--; + if ((mm->num_exe_file_vmas == 0) && mm->exe_file){ + fput(mm->exe_file); + mm->exe_file = NULL; + } + +} + +void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) +{ + if (new_exe_file) + get_file(new_exe_file); + if (mm->exe_file) + fput(mm->exe_file); + mm->exe_file = new_exe_file; + mm->num_exe_file_vmas = 0; +} + +struct file *get_mm_exe_file(struct mm_struct *mm) +{ + struct file *exe_file; + + /* We need mmap_sem to protect against races with removal of + * VM_EXECUTABLE vmas */ + down_read(&mm->mmap_sem); + exe_file = mm->exe_file; + if (exe_file) + get_file(exe_file); + up_read(&mm->mmap_sem); + return exe_file; +} + +void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm) +{ + /* It's safe to write the exe_file pointer without exe_file_lock because + * this is called during fork when the task is not yet in /proc */ + newmm->exe_file = get_mm_exe_file(oldmm); +} + +static int proc_exe_link(struct inode *inode, struct path *exe_path) +{ + struct task_struct *task; + struct mm_struct *mm; + struct file *exe_file; + + task = get_proc_task(inode); + if (!task) + return -ENOENT; + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) + return -ENOENT; + exe_file = get_mm_exe_file(mm); + mmput(mm); + if (exe_file) { + *exe_path = exe_file->f_path; + path_get(&exe_file->f_path); + fput(exe_file); + return 0; + } else + return -ENOENT; +} + static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; -- cgit v1.2.2